activity
20192025
most citedUnified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

4 citations · 7 across the 6 of their papers we have counts for

collaborators

7 papers

cs.RO2025

Neural Inertial Odometry from Lie Events

Royina Karegoudra Jayanth, Yinshuang Xu, Evangelos Chatzipantazis +2

Neural displacement priors (NDP) can reduce the drift in inertial odometry and provide uncertainty estimates that can be readily fused with off-the-shelf filters. However, they fai…

cs.CV2024★ 1 cited

Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation

Yinshuang Xu, Dian Chen, Katherine Liu +4

Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typi…

cs.RO2024★ 1 cited

EqNIO: Subequivariant Neural Inertial Odometry

Royina Karegoudra Jayanth, Yinshuang Xu, Ziyun Wang +3

Neural networks are seeing rapid adoption in purely inertial odometry, where accelerometer and gyroscope measurements from commodity inertial measurement units (IMU) are used to re…

cs.CV2022★ 1 cited

Equivariant Light Field Convolution and Transformer

Yinshuang Xu, Jiahui Lei, Kostas Daniilidis

3D reconstruction and novel view rendering can greatly benefit from geometric priors when the input views are not sufficient in terms of coverage and inter-view baselines. Deep lea…

cs.CV2022★ 4 cited

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces

Yinshuang Xu, Jiahui Lei, Edgar Dobriban +1

We introduce a unified framework for group equivariant networks on homogeneous spaces derived from a Fourier perspective. We consider tensor-valued feature fields, before and after…

cs.CV2020

Nested Scale Editing for Conditional Image Synthesis

Lingzhi Zhang, Jiancong Wang, Yinshuang Xu +4

We propose an image synthesis approach that provides stratified navigation in the latent code space. With a tiny amount of partial or very low-resolution image, our approach can co…